PageIndex · Issues· 105 open

Implementing PageIndex for Tabular Code Datasets in a GitHub RAG Chatbot

Please replace the deprecated PyPDF2 with PyPDF

[Bug]: Bare except in page_index_md.py masks underlying import and syntax errors

[Resource] GeoMind: Pre-indexed Knowledge Base Compatible with PageIndex Approach

Oversized first page produces an empty chunk that reaches the model

PyPDF2.errors.DependencyError: PyCryptodome is required for AES algorithm — crash on permission-only-encrypted PDFs (Flash preview)

Feature Request: Incremental Index Updates for Large Documents

Markdown path: below --summary-token-threshold, node text is copied verbatim into summary (undocumented; diverges from PDF path)

Bug: `get_leaf_nodes` raises KeyError on leaf nodes due to missing `nodes` key

Hello everyone, I have some questions regarding Hybrid Tree Search and would appreciate your insights.

No-TOC fallback uses entire source sentence as node title when no short heading exists

Sibling nodes on the same page get identical text → duplicate/near-duplicate summaries

can web just start a pageindex backend service,and use pageindex-py-sdk to manipulate the pageindex service。 And especially docker compose is better

Header elements overlap at widths above 1024px

Security Policy missing